Intelligent Workflow Research Articles

Leveraging artificial intelligence in Regulatory Technology (RegTech) for financial compliance

Abstract. The rapid development of Regulatory Technology (RegTech) has introduced new methods to handle and simplify the compliance and regulatory issues surrounding financial services and products. Combining artificial intelligence (AI) with this trend is an effective way of strengthening financial services, making them safer and more convenient. The current AI technologies incorporated within RegTech applications improve the efficiency of compliance with rules and regulations, and contribute to the development and implementation of smart technology, including automated regulatory reporting, proven and trustworthy KYC processes, and reduced compliance costs. This paper presents the application of intelligent technology, such as machine learning, deep learning, natural language processing, and smart regulatory frameworks, to build modern, intelligent workflows, dynamically control policies, and instantaneously monitor transactions. We employ empirical economic data, evidenced by realistic case studies, to demonstrate the benefits brought on by intelligent technology to financial institutions, including quicker compliance with regulatory regimes, decreased operational risk, and increased transparency and accountability. Through analysing figures offered in various cases, we show the transformed compliance landscape created by RegTech, how it becomes a solution for the diverse challenges affecting financial sectors on a global scale, and how is it going to impact the whole field of financial services in the future..

A deep learning-powered intelligent microdroplet analysis workflow for in-situ monitoring and evaluation of a dynamic emulsion

Accurately determining microdroplet size and uniformity in dispersed phase systems is key for assessing emulsion stability, and essential for quality monitoring and control of emulsion products. Microscopic imaging probes have provided intuitive and advanced insights for characterizing particle microscopic morphology and dispersion in multiphase flows. However, wide size distributions, edge-cutting, overlapping, and high-density target droplets can compromise the image processing accuracy, thereby affecting the precise assessment of emulsion status. In this study, we present a deep learning-based intelligent workflow for microdroplet characterization using an in-situ high-speed particle imaging probe combined with advanced image processing techniques. With the assistance of progressive automatic annotation, a droplet image database was constructed for training the Mask R-CNN model. By incorporating image patching and supervised data augmentation strategies, our well-trained model with accuracy of 95.5% can precisely detect, localize, and segment microscale droplets with various patterns. Additionally, the shape reconstruction module visualizes true shapes of overlapping and edge-cutting droplets, facilitating precise quantification of droplet size information. To validate the feasibility and generalizability of the proposed workflow, we obtained sufficient droplet images through offline sampling during emulsion processes while employing back and front illumination for in-situ monitoring. The automated method achieves precise droplet detection and size measurement, demonstrating its immense potential in online monitoring, evaluation, and control of emulsion quality.

From muscular to dexterous: A systematic review to understand the robotic taxonomy in construction and effectiveness

AbstractThis work presents an investigation of robotic technologies' effectiveness in construction activities. Sixty‐four highly relevant publications were identified from the database. By systematically reviewing the publications, the secondary data that are of interest to the review theme were retrieved and further evaluated. It is found that robotic technologies for automated construction is a growing field, where the taxonomy of robot was reflected in a diversified manner in the existing studies, ranging from the muscular guy—robotic manipulator—to the dexterous ones—unmanned aerial vehicle, autonomous mobile robot, automated guided vehicle, autonomous construction machinery and quadruped robot. In addition, the existing studies have provided substantial evidence to reveal the robotic technologies' effectiveness against traditional human methods in construction scenarios, and the measures for effectiveness consisted of productivity, precision, and success rate. With the evidence, it seems that the construction sector could benefit from robotic technologies to achieve intelligent workflows. Furthermore, based on the existing knowledge foundation in the current literature, a theoretical framework for future research direction is proposed. The framework envisages the integration of large models with construction robots to address operational inefficiencies, reduce costs, and simplify management.

Universal artificial intelligence workflow for factory energy saving: Ten case studies

Numerous studies have affirmed that artificial intelligence (AI) can effectively enable energy savings in factories. However, there is currently a lack of explicit research that identifies the energy-saving effects of AI methods as compared to the conventional practices employed in factories, which involve the replacement of equipment with high energy efficiency (non-AI method), with respect to variance in the effectiveness. Thus, this ignited the motivation for this study, wherein the research team developed a “Universal AI workflow for energy saving” which adopted a standard workflow of “learning, Modeling, and Prediction.” Additionally, a three-year research project was launched to conduct empirical tests in ten factories, comparing the efficacy differences between AI and Non-AI methods. In 2021, research team established the energy consumption baselines for each factory through data collection; the entirety of 2022 was dedicated to AI integrations; and energy-saving benefits were evaluated in 2023. During the research period, each factory also implemented other non-AI energy-saving methods which were juxtaposed with AI approaches for comparison. Our study results showed that average AI-enabled energy savings across the ten factories amounted to 106,124 kWh/yr, while average energy savings from non-AI methods amounted to 1,231,625 kWh/yr. Despite the inferior energy-saving results, the AI methods had an average return on investment (ROI) of 0.46 years while non-AI methods had an average ROI of 6.22 years, indicating that AI methods could recover the investment costs through energy savings in less than one year. It is also worth noting that the ten factories produced a diverse range of products encompassing wafers, steel, and foods, but the AI methods used for energy saving employed the same workflow. By contrast, the non-AI methods necessitated distinct workflows and detailed engineering adjustments. It can be inferred from these empirical findings that AI techniques for achieving energy-saving control in factories can be integrated using standardized processes. In summary, AI methods can facilitate standardized workflows in factories and offer substantial energy-saving benefits that can typically cover investments within a year. AI represents a highly viable energy conservation option for factories seeking to maintain uniformity in product processes and realize efficient ROIs.

The triassic formations of Kuwait: From geological concepts to numerical forward stratigraphic modelling applications

The Triassic exploration campaign onshore Kuwait initiated during the 1980s was mainly based on the evaluation of regional 2D seismic data. To date, few scattered wells have penetrated this succession reaching the Minjur, Jilh and Sudair mixed clastic and carbonate formations. The latter reservoirs are expected to hold potential gas and condensates that are yet to be proven. This communication aims at deciphering the spatial and temporal evolution of sedimentary architectures and associated Triassic depositional environments and facies along Kuwait. An integrated G&G assessment utilizing multi-disciplinary and multi-scale dataset allowed to identify the major petroleum system elements and develop sequential conceptual depositional models. The proposed models are then tested using numerical process-based forward stratigraphic applications. The seismic interpretation points to dominantly south to north oriented progradations centered on the Dibdibah low with thicknesses reaching around 1300 ft in the Sudair. In addition, progradations oriented from East to West highlight the location of the basin margins around the Kuwait Arch and its northern extension. These prograding tendencies are also identified in the overlying Jilh Formation. Onlapping reflectors point to transgressional systems related to flooding events that are expected to deposit marine fine-grained carbonatesand thus act as potential seals. Minjur Formation on the other hand, shows thick siliciclastic deposits along the southern sector of the Kuwait Arch. These fluvio-deltaic deposits are 150 feet thick and thin towards the west. Stratigraphic modelling allowed to test and constrain the paleobathymetric evolution of the system. The latter ranges between 0 and 20 m (inner ramp) and 20–40 m (Middle ramp) and reaches up to 80 m in the deeper sectors of the basin. The resultant facies at 3rd- 4th stratigraphic order highlights the evolution of lithologies and facies with regards to the various system tracts leading to a better understanding of the timing and spatial extent of mixed carbonate systems, evaporites and siliciclastics. Future works will focus on a higher resolution mapping of geobodies and prospects using integrated shared earth approaches including seismic multi-attribute assessment and 3D inversion and characterization driven by novel artificial intelligence workflows.

Computationally intelligent workflow for improved psychotherapy interventions: an ontology-based approach

Computationally intelligent workflow for improved psychotherapy interventions: an ontology-based approach

An artificial intelligence workflow for horizon volume generation from 3D seismic data

Horizon-based subsurface stratigraphic model building is a tedious process, especially in geologically complex areas where seismic data are contaminated with noise and thus are of weak and discontinuous reflectors. Seismic interpreters usually use stratal (proportional) slices to approximately inspect 3D seismic data along seismic reflectors yet to be interpreted. We introduce an artificial intelligence workflow consisting of three deep learning steps to provide a conditioned seismic image that is easier to interpret, a stratigraphic model that outlines major formations, and moreover a relative geologic time volume that allows us to automatically extract an infinite number of horizons along any seismic reflectors within a seismic cube. Depending on the availability of interpreters, the proposed workflow can either run fully unsupervised without human inputs or using sparse horizon interpretation as constraints to further improve the quality of extracted horizons, providing flexibility in both efficiency and quality. Starting from only seismic images and a few key horizons interpreted on very sparse seismic lines, we demonstrate the workflow to generate a stack of complete horizons covering the entire seismic volume from offshore Australia.

Enhancing Urban Landscape Design: A GAN-Based Approach for Rapid Color Rendering of Park Sketches

In urban ecological development, the effective planning and design of living spaces are crucial. Traditional color plan rendering methods, mainly using generative adversarial networks (GANs), rely heavily on edge extraction. This often leads to the loss of important details from hand-drawn drafts, significantly affecting the portrayal of the designer’s key concepts. This issue is especially critical in complex park planning. To address this, our study introduces a system based on conditional GANs. This system rapidly converts black-and-white park sketches into comprehensive color designs. We also employ a data augmentation strategy to enhance the quality of the output. The research reveals: (1) Our model efficiently produces designs suitable for industrial applications. (2) The GAN-based data augmentation improves the data volume, leading to enhanced rendering effects. (3) Our unique approach of direct rendering from sketches offers a novel method in urban planning and design. This study aims to enhance the rendering aspect of an intelligent workflow for landscape design. More efficient rendering techniques will reduce the iteration time of early design solutions and promote the iterative speed of designers’ thinking, thus improving the speed and efficiency of the whole design process.

Combining Machine Learning and Edge Computing: Opportunities, Challenges, Platforms, Frameworks, and Use Cases

In recent years, we have been observing the rapid growth and adoption of IoT-based systems, enhancing multiple areas of our lives. Concurrently, the utilization of machine learning techniques has surged, often for similar use cases as those seen in IoT systems. In this survey, we aim to focus on the combination of machine learning and the edge computing paradigm. The presented research commences with the topic of edge computing, its benefits, such as reduced data transmission, improved scalability, and reduced latency, as well as the challenges associated with this computing paradigm, like energy consumption, constrained devices, security, and device fleet management. It then presents the motivations behind the combination of machine learning and edge computing, such as the availability of more powerful edge devices, improving data privacy, reducing latency, or lowering reliance on centralized services. Then, it describes several edge computing platforms, with a focus on their capability to enable edge intelligence workflows. It also reviews the currently available edge intelligence frameworks and libraries, such as TensorFlow Lite or PyTorch Mobile. Afterward, the paper focuses on the existing use cases for edge intelligence in areas like industrial applications, healthcare applications, smart cities, environmental monitoring, or autonomous vehicles.

Enhancing mitosis quantification and detection in meningiomas with computational digital pathology

Mitosis is a critical criterion for meningioma grading. However, pathologists’ assessment of mitoses is subject to significant inter-observer variation due to challenges in locating mitosis hotspots and accurately detecting mitotic figures. To address this issue, we leverage digital pathology and propose a computational strategy to enhance pathologists’ mitosis assessment. The strategy has two components: (1) A depth-first search algorithm that quantifies the mathematically maximum mitotic count in 10 consecutive high-power fields, which can enhance the preciseness, especially in cases with borderline mitotic count. (2) Implementing a collaborative sphere to group a set of pathologists to detect mitoses under each high-power field, which can mitigate subjective random errors in mitosis detection originating from individual detection errors. By depth-first search algorithm (1) , we analyzed 19 meningioma slides and discovered that the proposed algorithm upgraded two borderline cases verified at consensus conferences. This improvement is attributed to the algorithm’s ability to quantify the mitotic count more comprehensively compared to other conventional methods of counting mitoses. In implementing a collaborative sphere (2) , we evaluated the correctness of mitosis detection from grouped pathologists and/or pathology residents, where each member of the group annotated a set of 48 high-power field images for mitotic figures independently. We report that groups with sizes of three can achieve an average precision of 0.897 and sensitivity of 0.699 in mitosis detection, which is higher than an average pathologist in this study (precision: 0.750, sensitivity: 0.667). The proposed computational strategy can be integrated with artificial intelligence workflow, which envisions the future of achieving a rapid and robust mitosis assessment by interactive assisting algorithms that can ultimately benefit patient management.

BIGOWL4DQ: Ontology-driven approach for Big Data quality meta-modelling, selection and reasoning

Context:Data quality should be at the core of many Artificial Intelligence initiatives from the very first moment in which data is required for a successful analysis. Measurement and evaluation of the level of quality are crucial to determining whether data can be used for the tasks at hand. Conscientious of this importance, industry and academia have proposed several data quality measurements and assessment frameworks over the last two decades. Unfortunately, there is no common and shared vocabulary for data quality terms. Thus, it is difficult and time-consuming to integrate data quality analysis within a (Big) Data workflow for performing Artificial Intelligence tasks. One of the main reasons is that, except for a reduced number of proposals, the presented vocabularies are neither machine-readable nor processable, needing human processing to be incorporated. Objective:This paper proposes a unified data quality measurement and assessment information model. This model can be used in different environments and contexts to describe data quality measurement and evaluation concerns. Method:The model has been developed as an ontology to make it interoperable and machine-readable. For better interoperability and applicability, this ontology, BIGOWL4DQ, has been developed as an extension of a previously developed ontology for describing knowledge management in Big Data analytics. Conclusions:This extended ontology provides a data quality measurement and assessment framework required when designing Artificial Intelligence workflows and integrated reasoning capacities. Thus, BIGOWL4DQ can be used to describe Big Data analysis and assess the data quality before the analysis. Result:Our proposal has been validated with two use cases. First, the semantic proposal has been assessed using an academic use case. And second, a real-world case study within an Artificial Intelligence workflow has been conducted to endorse our work.

A Deep Learning-Based Approach to Estimate Paneth Cell Granule Area in Celiac Disease.

Changes in Paneth cell numbers can be associated with chronic inflammatory diseases of the gastrointestinal tract. So far, no consensus has been achieved on the number of Paneth cells and their relevance to celiac disease (CD). To compare crypt and Paneth cell granule areas between patients with CD and those without CD (non-CD) using an artificial intelligence-based solution. Hematoxylin-eosin-stained sections of duodenal biopsies from 349 patients at the McGill University Health Centre were analyzed. Of these, 185 had a history of CD and 164 were controls. Slides were digitized, and NoCodeSeg, a code-free workflow using open-source software (QuPath, DeepMIB), was implemented to train deep learning models to segment crypts and Paneth cell granules. The total area of the entire analyzed tissue, epithelium, crypts, and Paneth cell granules was documented for all slides, and comparisons were performed. A mean intersection-over-union score of 88.76% and 91.30% was achieved for crypt areas and Paneth cell granule segmentations, respectively. On normalization to total tissue area, the crypt to total tissue area in CD was increased and the Paneth cell granule area to total tissue area decreased when compared to non-CD controls. Crypt hyperplasia was confirmed in CD compared to non-CD controls. The area of Paneth cell granules, an indirect measure of Paneth cell function, decreased with increasing severity of CD. More importantly, our study analyzed complete hematoxylin-eosin slide sections using an efficient and easy to use coding-free artificial intelligence workflow.

Artificial Intelligence (AI) Workflow for Catalyst Design and Optimization

Artificial Intelligence (AI) Workflow for Catalyst Design and Optimization

ОЦЕНКА УРОВНЯ ЦИФРОВОЙ ЗРЕЛОСТИ ПРЕДПРИЯТИЯ КАК ОДИН ИЗ ВАЖНЫХ ФАКТОРОВ В ЦИФРОВОЙ ТРАНСФОРМАЦИИ

The article is devoted to the issues of digital transformation, digital maturity and its assessment in enterprises. The article deals with digital maturity of enterprises, digital maturity levels, a comparative analysis of a number of approaches to determining digital maturity, the main directions for assessing digital maturity of enterprises. The aim of the study is to determine digital maturity level of the enterprise to implement software solutions. To achieve this aim, the author chooses a method for conducting the enterprise survey, compiling a digital maturity rating and constructing a radar chart. The scientific novelty of the article consists of determining the criteria for assessing digital maturity, which must be taken into account, as well as correctly analysing the survey results according to these criteria to determine digital maturity index of the enterprise. The following criteria are chosen as the study input: the leader’s vision, human resources, employee commitment (digital culture), flexible and secure infrastructure, data and analytics, intelligent workflows, models. The output data are the rating and assessment of digital maturity level of the enterprise. The processes described in the article contain new requirements of the digitalization era to the criteria for assessing digital maturity of the enterprise, which are a sign of the enterprise readiness for the successful implementation of digital transformation tasks.

An intelligent workflow for sub-nanoscale 3D reconstruction of intact synapses from serial section electron tomography

BackgroundAs an extension of electron tomography (ET), serial section electron tomography (serial section ET) aims to align the tomographic images of multiple thick tissue sections together, to break through the volume limitation of the single section and preserve the sub-nanoscale voxel size. It could be applied to reconstruct the intact synapse, which expands about one micrometer and contains nanoscale vesicles. However, there are several drawbacks of the existing serial section ET methods. First, locating and imaging regions of interest (ROIs) in serial sections during the shooting process is time-consuming. Second, the alignment of ET volumes is difficult due to the missing information caused by section cutting and imaging. Here we report a workflow to simplify the acquisition of ROIs in serial sections, automatically align the volume of serial section ET, and semi-automatically reconstruct the target synaptic structure.ResultsWe propose an intelligent workflow to reconstruct the intact synapse with sub-nanometer voxel size. Our workflow includes rapid localization of ROIs in serial sections, automatic alignment, restoration, assembly of serial ET volumes, and semi-automatic target structure segmentation. For the localization and acquisition of ROIs in serial sections, we use affine transformations to calculate their approximate position based on their relative location in orderly placed sections. For the alignment of consecutive ET volumes with significantly distinct appearances, we use multi-scale image feature matching and the elastic with belief propagation (BP-Elastic) algorithm to align them from coarse to fine. For the restoration of the missing information in ET, we first estimate the number of lost images based on the pixel changes of adjacent volumes after alignment. Then, we present a missing information generation network that is appropriate for small-sample of ET volume using pre-training interpolation network and distillation learning. And we use it to generate the missing information to achieve the whole volume reconstruction. For the reconstruction of synaptic ultrastructures, we use a 3D neural network to obtain them quickly. In summary, our workflow can quickly locate and acquire ROIs in serial sections, automatically align, restore, assemble serial sections, and obtain the complete segmentation result of the target structure with minimal manual manipulation. Multiple intact synapses in wild-type rat were reconstructed at a voxel size of 0.664 nm/voxel to demonstrate the effectiveness of our workflow.ConclusionsOur workflow contributes to obtaining intact synaptic structures at the sub-nanometer scale through serial section ET, which contains rapid ROI locating, automatic alignment, volume reconstruction, and semi-automatic synapse reconstruction. We have open-sourced the relevant code in our workflow, so it is easy to apply it to other labs and obtain complete 3D ultrastructures which size is similar to intact synapses with sub-nanometer voxel size.

Enhancing the drilling efficiency through the application of machine learning and optimization algorithm

This article presents a novel Artificial Intelligence (AI) workflow to enhance drilling performance by mitigating the adverse impact of drill-string vibrations on drilling efficiency. The study employs three supervised machine learning (ML) algorithms, namely the Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), and Regression Decision Tree (DTR), to train models for bit rotation (Bit RPM), rate of penetration (ROP), and torque. These models combine to form a digital twin for a drilling system and are validated through extensive cross-validation procedures against actual drilling parameters using field data.The combined SVR - Bit RPM model is then used to categorize torsional vibrations and constrain optimized parameter selection using the Particle Swarm Optimization block (PSO). The SVR-ROP model is integrated with a PSO under two constraints: Stick Slip Index (SSI<0.05) and Depth of Cut (DOC<5 mm) to further improve torsional stability. Simulations predict a 43% increase in ROP and torsional stability on average when the optimized parameters WOB and RPM are applied. This would avoid the need to trip in/out to change the bit, and the drilling time can be reduced from 66 to 31 h.The findings of this study illustrate the system's competency in determining optimal drilling parameters and boosting drilling efficiency. Integrating AI techniques offers valuable insights and practical solutions for drilling optimization, particularly in terms of saving drilling time and improving the ROP, which increases potential savings.

Seismic characterization of geologically complex geothermal reservoirs by combining structure-oriented filtering and attributes analysis

In geothermal systems, the geologic structure is a decisive factor in controlling fluid flow. Several geothermal systems around the world are located in complex geological structures, such as closely spaced and intersecting faults and fractures, folds, and dykes. Seismic data provides high-resolution images of complex structures that can be used to explore geothermal reservoirs. In fact, faults and fractures have subtle geologic edges that produce significant lateral variations in seismic data. Volumetric seismic attributes are quite effective for detecting these discontinuities in seismic data but are sensitive to noise and velocity accuracy. In North China, a deeply buried carbonate structure presents a geologically complex system with fault-controlled geothermal circulation. However, due to the deep burial depth and structural complexity, seismic reflection beneath the buried-hill has a low-quality, making it difficult to detect the characteristics of the fault edges. In this study, we first develop a structural architecture of the buried-hill carbonate reservoirs to show the development characteristics in vertical and plane directions. Next, we propose an intelligent workflow based on structure-oriented filtering and sensitive seismic attributes to investigate structural complexity (faults and fractures) in the basin for geothermal reservoir exploration. The results show that by combining the proposed structure-oriented filtering and sensitive volumetric seismic attributes, we can generate high-resolution seismic images to characterize fault edges, geometries, and fracture anomalies in structurally complex settings in order to identify upflow locations along the faults and fractures in geothermal systems. We further validated the fracture networks distribution by superimposing the extracted attributes with seismic fault networks and fracture density map using multilayer feedforward neural network. This workflow provides a reliable basis for the characterization of geothermal reservoirs in deep-buried and structurally controlled geothermal fields.

Neural network for the estimation of LFP battery SOH cycled at different power levels

This work presents a method to quantify and estimate the degradation level of lithium-ion battery cell cycle aged at different power levels. Experimental results previously reported by the authors are analysed further, now with artificial intelligence workflows to establish a method to estimate the cells degradation rate, in term of State of Health. The neural network estimation capability is dependent on the type of input signal used for training, and the relative proportion of training vs. testing data. The development of a feedforward neural network which elaborates the information of voltage and current differences during sudden power changes significantly increased the predictive capability of the method, reaching State-of-Health estimation best-case errors lower than 1 %, in line with more complex Artificial Intelligence approaches found in literature. In addition, the results obtained with the feedforward neural network are then compared with a regression learning – based estimation function, trained and tested over the same dataset. As last test, both these two methods, trained with dataset coming from cycle aging experimental tests, are used to estimate the State of Health of a lithium cell aged due to calendar phenomena only.

Intelligent Workflow and Software for Non-Target Analysis of Complex Samples Using a Mixture of Toxic Transformation Products of Unsymmetrical Dimethylhydrazine as an Example.

Unsymmetrical dimethylhydrazine (UDMH) is a widely used rocket propellant. Entering the environment or being stored in uncontrolled conditions, UDMH easily forms an enormous variety (at least many dozens) of transformation products. Environmental pollution by UDMH and its transformation products is a major problem in many countries and across the Arctic region. Unfortunately, previous works often use only electron ionization mass spectrometry with a library search, or they consider only the molecular formula to propose the structures of new products. This is quite an unreliable approach. It was demonstrated that a newly proposed artificial intelligence-based workflow allows for the proposal of structures of UDMH transformation products with a greater degree of certainty. The presented free and open-source software with a convenient graphical user interface facilitates the non-target analysis of industrial samples. It has bundled machine learning models for the prediction of retention indices and mass spectra. A critical analysis of whether a combination of several methods of chromatography and mass spectrometry allows us to elucidate the structure of an unknown UDMH transformation product was provided. It was demonstrated that the use of gas chromatographic retention indices for two stationary phases (polar and non-polar) allows for the rejection of false candidates in many cases when only one retention index is not enough. The structures of five previously unknown UDMH transformation products were proposed, and four previously proposed structures were refined.

Designing radiative cooling metamaterials for passive thermal management by particle swarm optimization

The passive radiative cooling technology shows a great potential application on reducing the enormous global energy consumption. The multilayer metamaterials could enhance the radiative cooling performance. However, it is a challenge to design the radiative cooler. In this work, based on the particle swarm optimization (PSO) evolutionary algorithm, we develop an intelligent workflow in designing photonic radiative cooling metamaterials. Specifically, we design two 10-layer SiO2 radiative coolers doped by cylindrical MgF2 or air impurities, possessing high emissivity within the selective (8–13 μm) and broadband (8–25 μm) atmospheric transparency windows, respectively. Our two kinds of coolers demonstrate power density as high as 119 W/m2 and 132 W/m2 at the room temperature (300 K). Our scheme does not rely on the usage of special materials, forming high-performing metamaterials with conventional poor-performing components. This significant improvement of the emission spectra proves the effectiveness of our inverse design algorithm in boosting the discovery of high-performing functional metamaterials.